A deep learning approach to increase the value of satellite data for PM2.5 monitoring in China
Abstract. Limitations in the current capability of monitoring PM2.5 adversely impact air quality management and health risk assessment of PM2.5 exposure. Commonly, ground-based monitoring networks are established to measure the PM2.5 concentrations in highly populated regions and protected areas such as national parks, yet large gaps exist in spatial coverage. Satellite-derived aerosol optical properties serve to complement the missing spatial information of ground-based monitoring networks. However, such attempts are hampered under cloudy/hazy conditions or during nighttime. Here we strive to overcome the long-standing restriction that surface PM2.5 cannot be constrained with satellite remote sensing under cloudy/hazy conditions or during nighttime. We introduce a deep spatiotemporal neural network (ST-NN) and demonstrate that it can artfully fill these observational gaps. We use sensitivity analysis and visualization technology to open the neural network black box data model, and quantitatively discuss the potential impact of the input data on the target variables. This technique provides ground-level PM2.5 concentrations with high spatial resolution (0.01°) and 24-hour temporal coverage. Better constrained spatiotemporal distributions of PM2.5 concentrations will help improve health effects studies, atmospheric emission estimates, and predictions of air quality.
Bo Li et al.
Status: final response (author comments only)
CC1: 'Comment on egusphere-2022-578', Hua Lin, 23 Aug 2022
- AC1: 'Reply on CC1', Bo Li, 25 Aug 2022
RC1: 'Comment on egusphere-2022-578', Anonymous Referee #1, 01 Sep 2022
- AC2: 'Reply on RC1', Bo Li, 21 Nov 2022
RC2: 'Comment on egusphere-2022-578', Anonymous Referee #2, 30 Sep 2022
- AC3: 'Reply on RC2', Bo Li, 21 Nov 2022
Bo Li et al.
MODIS land cover type https://doi.org/10.5067/MODIS/MCD12C1.006
MODIS aerosol optical depth https://doi.org/10.5067/MODIS/MOD04_3K.061
Himawari-8 satellite aerosol optical depth https://doi.org/10.2151/jmsj.2018-039
site pm2.5 http://www.cnemc.cn/
weather fields https://www.mmm.ucar.edu/weather-research-and-forecasting-model
road network https://download.geofabrik.de/asia/china.html
Bo Li et al.
Viewed (geographical distribution)
This study reported a study about obtaining the near-ground PM2.5 concentrations from satellite observation via deep learning method. The demonstration and verification of the article are sufficient for me. But, I still have several questions about this research:
1, The filtering method utilized in CNEMC dataset should be introduced in the manuscript. Besides, I wander how the filtered data affect the results?
2, What factors affect the training efficiency of ST-NN model? Does different learning rate have significant effect on training efficiency? How do you choose the learning rate?
3, Whether different optimizers affect the results? (SGD,Adam)
I find some typos in the Supplement:
Table. S10 spot and leisure services -> sport and leisure services
Table. S13 Rate (%) -> Rate